Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    plotting sin(x)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    3.11
    ::
    1.98
    :-
    1.95
    :**
    1.87
    :*
    1.86
    :\
    1.82
    -:
    1.81
    ：
    1.80
    :...
    1.78
    :>
    1.76
    POSITIVE LOGITS
     ܠ
    1.40
     Mientras
    1.37
     effectivement
    1.32
     ¡
    1.31
     PropTypes
    1.30
     Seeds
    1.29
     Agencia
    1.28
    न्दावन
    1.27
     การ
    1.27
     Una
    1.26
    Act Density 1.154%

    No Known Activations